• 한국항행학회논문지
• /
• 제15권1호
• /
• pp.130-139
• /
• 2011

본 논문에서는 HIS 칼라모델에서 색상변환을 이용한 자동차 추적 알고리즘을 제안 하였다. 제안된 알고리즘은 도로위에 두 개의 수평가상 데이터 샘플라인을 설치해 놓는다. 차영상은 프레임과 프레임 사이에서 검출하였다. 검출된 자동차의 차영상에서 색상 분포를 이용해서 자동차 동일성 판별과 차선 변경을 검출하였다. 제안된 알고리즘의 효능성을 검토하기 위하여 도로에 주행하는 자동차를 대상으로 두 가상 샘플라인을 통과하는 자동차의 동일성 판별과 차선 변경을 검출하고, 자동차의 속도 측정기와 제안된 방법을 비교한 결과 0.4% 이내임을 보였다.

• 한국도로학회논문집
• /
• 제19권2호
• /
• pp.25-34
• /
• 2017

PURPOSES: The purpose of this paper is to evaluate interface performance while using various tack coat materials for asphalt overlay. METHODS : The evaluation was conducted with tracking test, permeability, and interface bond strength. Tracking test was conducted using an image processing technique, to investigate the susceptibility of the tack coat materials. BBS and pull-off test were conducted to evaluate bond strength. The permeability test was conducted to evaluate the effect of tack coat materials. RESULTS : Results reveal that the trackless tack coat material demonstrates less tracking compared to other materials. Moreover, both BBS and pull-off tests can effectively evaluate the bond strength at the interface. RSC-4 was measured less bond strength. Moreover, tack coat prevents water penetration through the surface and aids the extension of the surface life of asphalt pavement. CONCLUSIONS : Trackless tack coat demonstrated a high and consistent bond strength performance. The tack coat types demonstrate marginally different performance as function of curing times. Field applicability was tested based on visual observation. Therefore, these should be considered when trackless tack coat is slightly enhanced the pavement performance based on limited this study results. Finally, it is necessary to allow reasonable time for the tack coat to completely cure.

• 한국도로학회논문집
• /
• 제15권1호
• /
• pp.57-63
• /
• 2013

PURPOSES: This study is to investigate the Hot In-Place recycling asphalt mixture in Korea using field produced materials. METHODS: Hot In-Place reclaimed asphalt mixture was investigated to evaluate the mixture properties based on various test results such as Marshall Test, Indirect Tensile Test, TSR, and Wheel Tracking Test. These test values were compared with domestic standard specification. RESULTS: The result of the laboratory experiment indicates that the Hot In-Place Reclaimed(HIR) asphalt mixture produced at the field constrution site was satisfied all of the test criteria such as Indirect tensile test, Marshall and TSR test, and wheel tracking test. During the test, the research team found that current HIR system is required an extention of mixing time to improve quality and to reduce variation of sample to sample. Although the current HIR mixture was passed the test criteria, there is a potential capability to enhance the mixture properties as extend mixting time. CONCLUSIONS: Based on these laboratory test results, It would be concluded that domestic HIR mixture's properties were satisfied all standard specification related with evaluation of recycling asphalt mixtures. Based on this case study result, there is a chance to save construction cost and increase the usage of reclaimed asphalt concrete in the future.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1669-1674
• /
• 2004

In this paper, a nonlinear information filter (IF) for curvilinear motions in an interacting multiple model (IMM) algorithm to track a maneuvering vehicle on a road is investigated. Driving patterns of vehicles on a road are modeled as stochastic hybrid systems. In order to track the maneuvering vehicles, two kinematic models are derived: A constant velocity model for linear motions and a constant-speed turn model for curvilinear motions. For the constant-speed turn model, a nonlinear IF is used in place of the extended Kalman filter in nonlinear systems. The suggested algorithm reduces the root mean squares error for linear motions and rapidly detects possible turning motions.

• International Journal of Automotive Technology
• /
• 제5권2호
• /
• pp.123-133
• /
• 2004

This paper describes a robust and fast wheel slip tracking control using a moving sliding surface technique. A traction control system (TCS) is the active safety system used to prevent the wheel slipping and thus improve acceleration performance, stability and steerability on slippery roads through the engine torque and/or brake torque control. This paper presents a wheel slip control for TCS through the engine torque control. The proposed controller can track a reference input wheel slip in a predetermined time. The design strategy investigated is based on a moving sliding surface that only contains the error between the reference input wheel slip and the actual wheel slip. The used moving sliding mode was originally designed to ensure that the states remain on a sliding surface, thereby achieving robustness and eliminating chattering. The improved robustness in driving is important due to changes, such as from dry road to wet road or vice versa which always happen in working conditions. Simulations are performed to demonstrate the effectiveness of the proposed moving sliding mode controller.

• 대한임베디드공학회논문지
• /
• 제3권3호
• /
• pp.143-150
• /
• 2008

In this paper, we investigate a real-time environment recognition system based on stereo vision for moving object. This system consists of stereo matching, obstacle detection and distance estimation. In stereo matching part, depth maps can be obtained real road images captured adjustable baseline stereo vision system using belief propagation(BP) algorithm. In detection part, various obstacles are detected using only depth map in case of both v-disparity and column detection method under the real road environment. Finally in estimation part, asymmetric parabola fitting with NCC method improves estimation of obstacle detection. This stereo vision system can be applied to many applications such as unmanned vehicle and robot.

• International Journal of Control, Automation, and Systems
• /
• 제2권3호
• /
• pp.310-318
• /
• 2004

In this paper, an unscented Kalman filter (UKF) for curvilinear motions in an interacting multiple model (IMM) algorithm to track a maneuvering vehicle on a road is investigated. Driving patterns of vehicles on a road are modeled as stochastic hybrid systems. In order to track the maneuvering vehicles, two kinematic models are derived: A constant velocity model for linear motions and a constant-speed turn model for curvilinear motions. For the constant-speed turn model, an UKF is used because of the drawbacks of the extended Kalman filter in nonlinear systems. The suggested algorithm reduces the root mean squares error for linear motions and rapidly detects possible turning motions.

• 한국전기전자재료학회논문지
• /
• 제27권12호
• /
• pp.841-846
• /
• 2014

It found that the maximum temperature of the arc discharge occurred on the Silicone rubber sample significantly decreased with increasing the reinforcing agent. It was confirmed that the current value decreased with increasing the aluminium trihydrate($Al(OH)_3$) and the current value increased with reducing the primary resistance over time. Regarding these results, may be it is because the degradation due to the electro-conductive carbonization was improved and the properties of dielectric breakdown was reduced by the flame retardant reinforcing agent. It found that the electro-conductive carbonized road has not happened by increasing the flame retardant reinforcing agent. Regarding to the arc discharge, this study show that the arc arising near the lower electrode of sample has disappeared.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제2권11호
• /
• pp.789-794
• /
• 2013

차량 추적 시스템(vehicle tracking system)은 교통 흐름 파악, 차량 감시, 사고 감지 등을 통하여 교통 정체에 따른 차량의 이동 경로를 유도할 수 있고, 교통사고를 사전에 방지할 수 있게 하는 시스템이다. 효과적인 차량 추적을 위해서는 먼저 연속된 영상 내의 각 객체의 특징 값을 추출하여 영상 내에 존재하는 차량 객체를 인지할 수 있어야 한다. 다음으로, 검출된 다중 객체에 대하여 영상 간 객체 매칭을 통해 연속된 프레임에 걸쳐 출현하는 동일한 차량을 인식함으로써 각 차량의 움직임을 추적할 수 있다. 본 논문에서는 차 영상의 이진화 및 레이블링(labeling)을 통하여 객체를 검출하고, 검출한 객체의 최소 외접 직사각형(minimum bounding rectangle: MBR)의 중심 좌표와 이 MBR의 가로, 세로 방향에 대한 라인(line)별 1D FFT(fast Fourier transform) 변환 결과의 평균 계수 값을 계산하여 객체의 특징 값을 구한다. 다음으로, 연속된 프레임에 걸쳐 출현하는 객체들 중 유사도가 가장 높은 객체 쌍을 동일한 객체로 인식하여 객체를 추적하는 방법을 제안한다. 실험 결과, 제안한 방법은 객체의 기하학적 특성에 기초한 기존 방법들에 비하여 정확한 추적이 가능함을 보여주었다.

• 전자공학회논문지
• /
• 제49권12호
• /
• pp.265-274
• /
• 2012

본 논문에서는 레이더와 비전센서 융합 기반의 움직임추정을 이용한 전방차량 검출 및 추적 방법을 제안한다. 제안하는 방법은 움직임추정을 통하여 레이더로 관측한 타겟의 부정확한 횡방향 위치를 보정할 뿐만 아니라 자차의 거동에 따른 자차-지면 간의 기하학적 관계 변화에 적응적으로 전방차량을 검출하고 추적한다. 또한 연산량 부담이 적은 특징점기반의 움직임추정 방법을 사용하여 차량을 검증하는 과정의 수행 횟수 감소를 도모하였다. 제안하는 움직임추정 방법으로 보정한 타겟이 기존의 방법에 비해 높은 시간적 일관성(temporal consistency)을 가지고 전방차량을 추적하는 것은 물론 다양한 도로환경에서 강건하게 전방차량을 검출하는 것을 실험을 통해 입증하였다.